Search

Applying machine learning (ML) to objective markers may overcome prognosis uncertainty due to the subjective nature of the diagnosis of bipolar disorder (BD). This PRISMA-compliant meta-analysis provides new systematic evidence of the BD classification accuracy reached by different markers and ML algorithms. We focused on neuroimaging, electrophysiological techniques, peripheral biomarkers, genetic data, neuropsychological or clinical measures, and multimodal approaches. PubMed, Embase and Scopus were searched through 3rd December 2020. Meta-analyses were performed using random-effect models. Overall, 81 studies were included in this systematic review and 65 in the meta-analysis (11,336 participants, 3903 BD). The overall pooled classification accuracy was 0.77 (95%CI[0.75;0.80]). Despite subgroup analyses for diagnostic comparison group, psychiatric disorders, marker, ML algorithm, and validation procedure were not significant, linear discriminant analysis significantly outperformed support vector machine for peripheral biomarkers (p = 0.03). Sample size was inversely related to accuracy. Evidence of publication bias was detected. Ultimately, although ML reached a high accuracy in differentiating BD from other psychiatric disorders, best practices in methodology are needed for the advancement of future studies.

Background Dialectical Behavior Therapy Skills Training (DBT-ST) as stand-alone treatment has demonstrated promising outcomes for the treatment of alcohol use disorder (AUD) and concurrent substance use disorders (SUDs). However, no studies have so far empirically investigated factors that might predict efficacy of this therapeutic model. Methods 275 treatment-seeking individuals with AUD and other SUDs were consecutively admitted to a 3-month DBT-ST program (in- + outpatient; outpatient settings). The machine learning routine applied (i.e. penalized regression combined with a nested cross-validation procedure) was conducted in order to estimate predictive values of a wide panel of clinical variables in a single statistical framework on drop-out and substance-use behaviors, dealing with related multicollinearity, and eliminating redundant variables. Results The cross-validated elastic net model significantly predicted the drop-out. The bootstrap analysis revealed that subjects who showed substance-use behaviors during the intervention and who were treated with the mixed setting (i.e., in- and outpatient) program, together with higher ASI alcohol scores were associated with an higher probability of drop-out. On the contrary, older subjects, higher levels of education, together with higher scores of DERS awareness subscale were negatively associated to drop-out. Similarly, lifetime co-diagnoses of anxiety, bipolar, and gambling disorders, together with bulimia nervosa negatively predicted the drop-out. The machine learning model did not identify predictive variables of substance-use behaviors during the treatment. Conclusions The DBT-ST program could be considered a valid therapeutic approach especially when AUD and other SUDs co-occur with other psychiatric conditions and, it is carried out as a full outpatient intervention.